From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757961AbaGALO3 (ORCPT ); Tue, 1 Jul 2014 07:14:29 -0400 Received: from e23smtp08.au.ibm.com ([202.81.31.141]:52327 "EHLO e23smtp08.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757894AbaGALO0 (ORCPT ); Tue, 1 Jul 2014 07:14:26 -0400 Message-ID: <53B2974A.6010809@linux.vnet.ibm.com> Date: Tue, 01 Jul 2014 16:41:06 +0530 From: Raghavendra K T Organization: IBM User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/20130625 Thunderbird/17.0.7 MIME-Version: 1.0 To: Peter Zijlstra CC: tglx@linutronix.de, mingo@redhat.com, hpa@zytor.com, konrad.wilk@oracle.com, pbonzini@redhat.com, gleb@redhat.com, paulmck@linux.vnet.ibm.com, torvalds@linux-foundation.org, waiman.long@hp.com, riel@redhat.com, davej@redhat.com, oleg@redhat.com, x86@kernel.org, jeremy@goop.org, paul.gortmaker@windriver.com, ak@linux.intel.com, jasowang@redhat.com, fernando_b1@lab.ntt.co.jp, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, virtualization@lists.linux-foundation.org, xen-devel@lists.xenproject.org, mtosatti@redhat.com, chegu_vinod@hp.com Subject: Re: [RFC PATCH v2] Implement Batched (group) ticket lock References: <1403947024-3193-1-git-send-email-raghavendra.kt@linux.vnet.ibm.com> <20140701080537.GH6758@twins.programming.kicks-ass.net> <53B282E9.6060806@linux.vnet.ibm.com> <20140701095521.GO6758@twins.programming.kicks-ass.net> In-Reply-To: <20140701095521.GO6758@twins.programming.kicks-ass.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 14070111-5140-0000-0000-00000568E004 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org >> >> For baremetal we continue to have 'fully fair ticketlock' with this patch >> series. >> > > But but but, we're looking at removing ticket locks. So why do we want > to invest in them now? > I have nothing against qspinlock. I am happy to test it/add any bit to it if I could. With this patch we get excellent performance for guest with the unmodified kernel without affecting host. My test on guest with batch_size =16,32 showed even better performance bs=16 bs=32 ebizzy_0.5x 0.14 0.90 ebizzy_1.0x 3.57 7.52 ebizzy_1.5x 58.97 67.65 ebizzy_2.0x 121.55 136.45